Skills/npm/mcp-server

mcp-server@0.8.8

VERIFIED

Publisher claims: "Transloadit MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher transloadit · publishing for 285 daysInstalls 12,074Last detonated 13 h ago
$claude mcp add mcp-server -- npx -y @transloadit/mcp-server
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
TRANSLOADIT_MCP_METRICS_PASSWORDTRANSLOADIT_MCP_TOKENTRANSLOADIT_MCP_UPSTREAM_SECRETTRANSLOADIT_SECRETConfiguration, not credentials: TRANSLOADIT_CLIENT_SUFFIX, TRANSLOADIT_ENDPOINT, TRANSLOADIT_KEY, TRANSLOADIT_MCP_CONSOLE_URL, TRANSLOADIT_MCP_MAX_WAIT_MS, TRANSLOADIT_MCP_METRICS_PATH, TRANSLOADIT_MCP_METRICS_USER, TRANSLOADIT_MCP_RESOURCE_METADATA_URL, TRANSLOADIT_MCP_RESULT_DOMAINS, TRANSLOADIT_MCP_WIDGET_DOMAIN, TRANSLOADIT_SIGNATURE_ALGORITHM
Where it talks to
transloadit.com, transloadit.dev, transloadit.net (its own)Also chatgpt.com, claude.ai, claude.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names chatgpt.com, claude.ai, claude.com as well as its own vendor. The guard injects TRANSLOADIT_MCP_METRICS_PASSWORD, TRANSLOADIT_MCP_TOKEN, TRANSLOADIT_MCP_UPSTREAM_SECRET, TRANSLOADIT_SECRET only into requests to transloadit.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets TRANSLOADIT_MCP_METRICS_PASSWORD=transloadit.com,TRANSLOADIT_MCP_TOKEN=transloadit.com,TRANSLOADIT_MCP_UPSTREAM_SECRET=transloadit.com,TRANSLOADIT_SECRET=transloadit.com -- npx -y @transloadit/mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-14 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 33 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
12sprocessdependency install exit 0
32sclaimed8 tools: transloadit_lint_assembly_instructions, transloadit_create_assembly, transloadit_get_assembly_status, transloadit_wait_for_assembly, transloadit_list_robots, transloadit_get_robot_help, transloadit_list_templates, transloadit_get_profile
32stools5c7b58505ed5e93c
32stools15bb647410b62745
32stools203c7d953c885380
32stoolscf9beeda48ec0920
32stools71d5643c9b116cb3
32stools927b1d0b392d7392
32stools73df93c3ed99f544
32stoolsfd0dd5adf0d8e808
32sprocessscript backend runs setup only
32sprocessno install scripts to re-run

Static findings

LOW
Prompt injectionREADME.md:43 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileSettings → Apps & Connectors → Advanced → Developer mode → Create, then enter the URL above withFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:43 · Authorization escalation language · informational: not an instruction fileSettings → Apps & Connectors → Advanced → Developer mode → Create, then enter the URL above withFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)dist/ui/assembly-result-widget.d.ts:58 · MCP server using network transport (SSE/HTTP) — data sent over networkexport declare const registerAssemblyResultWidget: (server: McpServer, options?: AssemblyResultWidgetOptions) => void;Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File permission modification commandpackage.json:57 · File permission modification command — agent changes file ownership/permissions"build": "yarn lint:ts && chmod +x dist/cli.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedist/server.js:1336 · npx invocation of non-well-known package — may execute untrusted codehint: 'Retry with base64 or a public URL, or upload via `npx -y @transloadit/node upload`.',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈44 tok
1 file · 39 in bundle
Tool list per prompt
≈1,431 tok
8 tools · 179 per tool
Handshake
1978 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 214

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for @transloadit/mcp-server@0.8.8 as of 12 h ago. This is the package itself, not its dependencies.